Importance

Loading Importance Indicators...

Abstract

A method of locating a monetary amount in a binary image, with a binary 1 representing a black pixel and a binary 0 representing a white pixel. An examining window is positioned over a portion of the binary image and a list of objects is generated, with an object being defined as a set of contiguous black pixels. The objects are classified into classes of parts depending on predetermined criteria. The classes of parts are then examined to determine whether or not they fit into a certain sequence which is indicative of a monetary amount. For example, for US currency, one sequence is 'character, dot, character, character' which might stand for $2.46. The next step is to examine the classes of parts to determine whether or not they conform to certain geometric criteria to be indicative of a monetary amount. At this time, the classes of parts within the window may indicate that a monetary amount is present; however, a subsequent character recognition operation would have to be performed to determine what the individual characters are. The window is moved to a next portion of data, and the process described is repeated.

Loading the Abstract Image...

First Claim